- Title: Universal Assistant Behavior Standards (PIVOT Edition)
- Version: 1.1
- Last Updated: 24-07-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Less Rain GmbH
- Tags: assistant-behavior, prompt-engineering, modular, workflow, transparency, collaboration, reflection, user-centered, iteration
- License: MIT
Luis Alberto Martinez arenagroove
arenagroove
/ 01-universal-assistant-behavior-standards.md
Last active
July 24, 2025 14:45
Universal behavior rules for AI assistants — coherent, user-directed, context-aware, multitask-ready, and respectful of role, boundaries, and feedback.
arenagroove
/ canary-token-chatgpt-guide.md
Last active
July 26, 2025 06:09
Compliance test for synthetic canary tokens in ChatGPT, including a prompt, step-by-step instructions, and memory notes.
- Title: Testing Canary Tokens for Compliance in ChatGPT: Step-by-Step Guide
- Version: 1.0
- Last Updated: 17-07-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Part of independent R&D and AI prompt development at Less Rain GmbH
- Tags: canary-token, compliance, ChatGPT, audit, prompt-engineering, memory, data-governance, privacy
- License: MIT
arenagroove
/ Lesser-Known-LinkedIn-Visibility-Tactics.md
Last active
July 20, 2025 05:50
Uncommon LinkedIn tactics to boost visibility, engagement, and reach—each with strengths and weaknesses, explained for 2025 networking.
This table summarizes subtle, research-backed tactics that go beyond the usual LinkedIn “like, comment, share” advice. Each tactic is designed to help you gain more public reach, keep your posts and comments visible longer, and spark richer professional conversations—while working with the LinkedIn algorithm, not against it.
Who is this for?
Anyone seeking genuine network growth and discussion on LinkedIn, and interested in making their content more discoverable, not just buried in a small circle. Use this to refine your public engagement strategy.
| Tactic | Why It Boosts Algorithmic Visibility | Strengths | Weaknesses |
arenagroove
/ 01-lyric-to-post-prompt.md
Last active
July 21, 2025 08:56
You are an advanced assistant that helps users reflect on the meaning of a song lyric by composing a creative or personal social media post. You never simulate personality unless explicitly instructed. You shape your behavior entirely from the user’s inputs and follow strict privacy and tone integrity rules.
Before any interpretation, post generation, or lyric analysis:
arenagroove
/ custom-gpt-audit.md
Last active
July 23, 2025 09:09
Audit prompts and protection strategies for Custom GPTs: how to extract, test, and defend against prompt leakage
Modern Custom GPTs (e.g., OpenAI’s ChatGPT GPTs, Claude, Gemini, etc.) offer great flexibility, but are prone to leaking their system prompts, instructions, and knowledge files via user prompts. This document is a practical reference on auditing, reverse-engineering, and especially protecting custom GPTs, summarizing methods and best practices confirmed across communities and research.
arenagroove
/ 01-linkedin-narrative-audit.md
Last active
August 12, 2025 04:06
Advanced prompt for AI-powered LinkedIn content audits. Supports partial uploads, enforces privacy, analyzes voice, tone, media, and audience clusters. Rewrite-focused and future-proof.
- Title: LinkedIn Narrative Audit: Symbolic Influence, Voice, and Audience Self-Analysis
- Version: 1.4
- Last Updated: 13-08-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Independent R&D and AI prompt development at Less Rain GmbH
- Tags: linkedin, audit, personal-brand, AI-prompt, privacy, voice-analysis, symbolic-capital, content-strategy, psycholinguistics, prompt-engineering
arenagroove
/ ffmpeg-copilot-prompt.md
Created
July 26, 2025 06:05
Universal LLM prompt for safe and modern FFmpeg scripting: batch video/audio/image/media automation, CLI-ready, with explanations, risk flags, and OS-compatible logic.
- Title: FFmpeg & Media Operations Copilot Prompt
- Version: 1.0
- Last Updated: 26-07-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Part of independent R&D and AI prompt development at Less Rain GmbH
- GitHub Repository: github.com/arenagroove/ffmpeg-copilot
- Tags: ffmpeg, prompt-engineering, media, ai-tools, automation, scripting, copilot
- License: MIT License
arenagroove
/ 00-conversations-that-algorithms-dont-understand.md
Last active
July 27, 2025 04:00
A quiet diner, a conversation about justice, and the kind of noise algorithms add when they don’t understand what’s at stake.
- Title: Conversations That Algorithms Don’t Understand – Narrative and Prompt
- Version: 1.0
- Last Updated: 27-07-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Independent R&D and assistant prompt design at Less Rain GmbH
- GitHub Repository: To be added if published
- Tags: ai-dialogue, narrative-prompts, assistant-design, symbolic-scenes, algorithmic-satire, roleplay-simulation
- License: MIT License
arenagroove
/ 00-technology-ethics-critical-reflection-prompt.md
Last active
July 27, 2025 06:12
- Title: Technology Ethics Critical Reflection Prompt (2025, Hard Mode)
- Version: 1.0
- Last Updated: 27-07-2025
- Author: Luis Alberto Martinez Riancho (@arenagroove)
- Affiliation: Independent R&D and assistant prompt design at Less Rain GmbH
- Tags: ai-ethics, reflection-prompts, systemic-design, creative-complicity, assistant-scaffolds, hard-mode
- License: MIT License
arenagroove
/ 01-README-lr-llms-txt-generator.md
Last active
August 10, 2025 02:09
Dynamic llms.txt generator for WordPress: paginated, cached, supports multilingual sites (Polylang/WPML), post type & post ID exclusion, and is configurable via admin UI. Output and logic are further customizable using developer filters. Optimized for LLM crawler indexing and large sites.
Creates a public, multilingual, paginated llms.txt endpoint for Large Language Model (LLM) crawlers to discover URLs on your WordPress site.
Provides admin controls for exclusions, headings/descriptions, caching, and an extended set of developer filters for deep customization.
- Public endpoint:
/llms.txt— Always accessible, no authentication